Hate begets Hate

Mathew, Binny; Illendula, Anurag; Saha, Punyajoy; Sarkar, Soumya; Goyal, Pawan; Mukherjee, Animesh

doi:10.1145/3415163

Cited by 55 publications

(21 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While examplars help obtain latent signals from within the dataset, users' propensity for posting hateful content is not just a one-time incident. Users who interact with similarly malicious users are likely to disseminate hateful content online regularly and more likely to post offensive content than their benign counterparts [37]. Thus, a user's historical data provides crucial insights into whether they will post hostile material in the future [45].…”

Section: Timeline Modulementioning

confidence: 99%

See 1 more Smart Citation

Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment

Kulkarni

Masud

Goyal

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Social media is awash with hateful content, much of which is often veiled with linguistic and topical diversity. The benchmark datasets used for hate speech detection do not account for such divagation as they are predominantly compiled using hate lexicons. However, capturing hate signals becomes challenging in neutrally-seeded malicious content. Thus, designing models and datasets that mimic the real-world variability of hate warrants further investigation.To this end, we present GOTHate, a large-scale code-mixed crowdsourced dataset of around 51𝑘 posts for hate speech detection from Twitter. GOTHate is neutrally seeded, encompassing different languages and topics. We conduct detailed comparisons of GOTHate with the existing hate speech datasets, highlighting its novelty. We benchmark it with 10 recent baselines. Our extensive empirical and benchmarking experiments suggest that GOTHate is hard to classify in a text-only setup. Thus, we investigate how adding endogenous signals enhances the hate speech detection task. We augment GOTHate with the user's timeline information and ego network, bringing the overall data source closer to the real-world setup for understanding hateful content. Our proposed solution HEN-mBERT, is a modular, multilingual, mixture-of-experts model that enriches the linguistic subspace with latent endogenous signals from history, topology, and exemplars. HEN-mBERT transcends the best baseline by 2.5% and 5% in overall macro-F1 and hate class F1, respectively. Inspired by our experiments, in partnership with Wipro AI, we are developing a semi-automated pipeline to detect hateful content as a part of their mission to tackle online harm. 1 CCS CONCEPTS• Computing methodologies → Language resources; Supervised learning by classification.

show abstract

Section: Timeline Modulementioning

confidence: 99%

“…Intuition. Hateful users are likelier to follow and retweet other toxic users [37,48]. Therefore, we examine their ego network and extract their interaction patterns.…”

Section: Graph Modulementioning

confidence: 99%

Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment

Kulkarni

Masud

Goyal

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…Temporal movement of users. To understand the temporal influence of the users over the entire timeline, we utilise the follower-followee network per month which was referred to in (56). Then for each month we calculate the k-core or coreness metric (29) to identify the influential users in the undirected version of the follower-followee network.…”

Section: Post Classificationmentioning

confidence: 99%

On the rise of fear speech in online social media

Saha,

Garimella,

Kalyan

et al. 2023

Preprint

View full text Add to dashboard Cite

Recently, social media platforms are heavily moderated to prevent the spread of online hate speech (1) which is usually fertile in toxic words and is directed toward an individual or a community. Owing to such heavy moderation newer and more subtle techniques are being deployed. One of the most striking among these is fear speech (2). Fear speech, as the name suggests, attempts to incite fear about a target community (3). Although subtle, it might be highly effective often pushing communities toward a physical conflict (2). Therefore, understanding their prevalence in social media is of paramount importance. This article presents a large-scale study to understand the prevalence of 400K fear speech over 700K hate speech posts collected from Gab.com. Remarkably, users posting large number of fear * https://transparency.fb.com/en-gb/policies/community-standards/hate-speech/ † ttps://help.twitter.com/en/rules-and-policies/hateful-conduct-policy

show abstract

“…In order to perform transfer learning in this scenario, all the hate speech detection models are trained on recently published manually annotated data for hate speech detection, called HateXplain (Mathew et al 2020). Similar to previous studies on hate speech detection, the sources of the dataset are Twitter (Waseem and Hovy 2016;Davidson et al 2017;Founta et al 2018) and Gab (Mathew et al 2019). All the data are annotated using Amazon Mechanical Turk (MTurk) where each text is annotated based on: (1) whether it is hate speech, offensive speech, or normal; (2) the target communities in the text, including target groups such as Race, Religion, Gender, Sexual Orientation, and Miscellaneous;…”

Section: Hate Speech Detectionmentioning

confidence: 99%

Analyzing social media for measuring public attitudes toward controversies and their driving factors: a case study of migration

Chen

Sack

Alam

2022

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

Among other ways of expressing opinions on media such as blogs, and forums, social media (such as Twitter) has become one of the most widely used channels by populations for expressing their opinions. With an increasing interest in the topic of migration in Europe, it is important to process and analyze these opinions. To this end, this study aims at measuring the public attitudes toward migration in terms of sentiments and hate speech from a large number of tweets crawled on the decisive topic of migration. This study introduces a knowledge base (KB) of anonymized migration-related annotated tweets termed as (MGKB). The tweets from 2013 to July 2021 in the European countries that are hosts of immigrants are collected, pre-processed, and filtered using advanced topic modeling techniques. BERT-based entity linking and sentiment analysis, complemented by attention-based hate speech detection, are performed to annotate the curated tweets. Moreover, external databases are used to identify the potential social and economic factors causing negative public attitudes toward migration. The analysis aligns with the hypothesis that the countries with more migrants have fewer negative and hateful tweets. To further promote research in the interdisciplinary fields of social sciences and computer science, the outcomes are integrated into MGKB, which significantly extends the existing ontology to consider the public attitudes toward migrations and economic indicators. This study further discusses the use-cases and exploitation of MGKB. Finally, MGKB is made publicly available, fully supporting the FAIR principles.

show abstract

Hate begets Hate

Cited by 55 publications

References 25 publications

Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment

Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment

On the rise of fear speech in online social media

Analyzing social media for measuring public attitudes toward controversies and their driving factors: a case study of migration

Contact Info

Product

Resources

About